arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.05877cs.CRcs.AIcs.LG
收藏

Fabricated Flips: 无需数据即可毒化联邦学习

Fabricated Flips: Poisoning Federated Learning without Data

TU Delft(代尔夫特理工大学)

Jiyue Huang, Zilong Zhao, Lydia Y. Chen, Stefanie Roos

AI总结:

本文提出无数据无目标攻击DFA(含DFA-R和DFA-G两种变体),通过合成恶意数据构建对抗模型,无需窃听或大量特定数据即可有效毒化联邦学习,并设计了REFD防御机制以检测和过滤此类恶意更新。

摘要:

对联邦学习(FL)的攻击会严重降低生成模型的质量,并限制这种支持本地去中心化学习的新兴学习范式的实用性。然而,现有的无目标攻击在许多场景中并不实用,因为它们假设:i) 攻击者知道良性客户端的每一次更新,或者 ii) 攻击者拥有一个大型数据集来在本地训练模仿良性参与方的更新。在本文中,我们提出了一种无数据无目标攻击(DFA),它合成恶意数据来构建对抗模型,完全不需要窃听良性客户端的传输,也不需要大量特定任务的训练数据。我们设计了两种DFA变体,即DFA-R和DFA-G,它们在如何权衡隐蔽性和有效性方面有所不同。具体而言,DFA-R迭代地优化一个恶意数据层,以最小化全局模型所有输出的预测置信度,而DFA-G则通过将全局模型的输出引导至特定类别,交互式地训练一个恶意数据生成器网络。在Fashion-MNIST、Cifar-10和SVHN上的实验结果表明,尽管DFA所需的假设少于现有攻击,但其在对抗各种最先进防御机制时,攻击成功率与最先进的无目标攻击相似甚至更高。具体来说,在CIFAR-10上,它们能在至少50%的情况下规避所有考虑的防御机制,并且通常将准确率降低2倍以上。因此,我们设计了REFD,一种专门为防御无数据攻击而设计的防御机制。REFD利用参考数据集来检测有偏差或置信度低的更新。它通过过滤掉恶意更新,极大地改进了现有防御方法,并实现了较高的全局模型准确率。

英文摘要:

Attacks on Federated Learning (FL) can severely reduce the quality of the generated models and limit the usefulness of this emerging learning paradigm that enables on-premise decentralized learning. However, existing untargeted attacks are not practical for many scenarios as they assume that i) the attacker knows every update of benign clients, or ii) the attacker has a large dataset to locally train updates imitating benign parties. In this paper, we propose a data-free untargeted attack (DFA) that synthesizes malicious data to craft adversarial models without eavesdropping on the transmission of benign clients at all or requiring a large quantity of task-specific training data. We design two variants of DFA, namely DFA-R and DFA-G, which differ in how they trade off stealthiness and effectiveness. Specifically, DFA-R iteratively optimizes a malicious data layer to minimize the prediction confidence of all outputs of the global model, whereas DFA-G interactively trains a malicious data generator network by steering the output of the global model toward a particular class. Experimental results on Fashion-MNIST, Cifar-10, and SVHN show that DFA, despite requiring fewer assumptions than existing attacks, achieves similar or even higher attack success rate than state-of-the-art untargeted attacks against various state-of-the-art defense mechanisms. Concretely, they can evade all considered defense mechanisms in at least 50% of the cases for CIFAR-10 and often reduce the accuracy by more than a factor of 2. Consequently, we design REFD, a defense specifically crafted to protect against data-free attacks. REFD leverages a reference dataset to detect updates that are biased or have a low confidence. It greatly improves upon existing defenses by filtering out the malicious updates and achieves high global model accuracy

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑